Run 2. Outer Step 6. Inner Step 536.

config.json

@@ -268,18 +268,18 @@
     "AutoModelForCausalLM": "distributed/optimized-gpt2-500m--modeling_gpt_optimized.GPTOptim"
   },
   "block_list": [
-    5337327,
-    5337332,
-    5337336,
-    5337340,
-    5337345
+    5337376,
+    5337380,
+    5337384,
+    5337388,
+    5337393
   ],
   "block_size": 1024,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "initializer_range": 0.02,
-  "inner_step": 529,
+  "inner_step": 536,
   "inner_steps": 0,
   "last_allreduce_block": 5330632,
   "layer_norm_epsilon": 1e-05,

inner_optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03d8a30d04529d16cd67f45d2f4bf7ffa376a306679400fb457df39d51fdb65
+oid sha256:7bf7d4910ff6d4da0aaed8b903255883db4a054bd11414017da33241ef9b1d99
 size 8081782026

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8152cd1d77e7c0602cd17e0d56688a74b587d657cf89744067e4f9f9b094ad98
+oid sha256:752597c6fc5f92c6b62075145ed7b8bbfabb5a66b83276000f11038c74b4f1df
 size 4040701744